Related papers: AI Alignment Dialogues: An Interactive Approach to…
A common vision from science fiction is that robots will one day inhabit our physical spaces, sense the world as we do, assist our physical labours, and communicate with us through natural language. Here we study how to design artificial…
Instruction-tuned Large Language Models (LLMs) are increasingly deployed as AI Assistants in firms for support in cognitive tasks. These AI assistants carry embedded perspectives which influence factors across the firm including…
For artificial intelligence to be beneficial to humans the behaviour of AI agents needs to be aligned with what humans want. In this paper we discuss some behavioural issues for language agents, arising from accidental misspecification by…
One of the long-term goals of artificial intelligence is to build an agent that can communicate intelligently with human in natural language. Most existing work on natural language learning relies heavily on training over a pre-collected…
Artificially intelligent agents are increasingly being integrated into human decision-making: from large language model (LLM) assistants to autonomous vehicles. These systems often optimize their individual objective, leading to conflicts,…
As artificial intelligence scales, the concepts of alignment, agency, and autonomy have become central to AI safety, governance, and control. However, even in human contexts, these terms lack universal definitions, varying across…
Meaningful human-AI collaboration requires more than processing language; it demands a deeper understanding of symbols and their socially constructed meanings. While humans naturally interpret symbols through social interaction, AI systems…
Deep neural networks excel in medical imaging but remain prone to biases, leading to fairness gaps across demographic groups. We provide the first systematic exploration of Human-AI alignment and fairness in this domain. Our results show…
While we do not always use words, communicating what we want to an AI is a conversation -- with ourselves as well as with it, a recurring loop with optional steps depending on the complexity of the situation and our request. Any given…
A leading proposal for aligning artificial superintelligence (ASI) is to use AI agents to automate an increasing fraction of alignment research as capabilities improve. We argue that, even when research agents are not scheming to…
We describe cases where real recommender systems were modified in the service of various human values such as diversity, fairness, well-being, time well spent, and factual accuracy. From this we identify the current practice of values…
There is a resurgent interest in developing intelligent open-domain dialog systems due to the availability of large amounts of conversational data and the recent progress on neural approaches to conversational AI. Unlike traditional…
The issues of AI risk and AI safety are becoming critical as the prospect of artificial general intelligence (AGI) looms larger. The emergence of extremely large and capable generative models has led to alarming predictions and created a…
We conducted an International AI Negotiation Competition in which participants designed and refined prompts for AI negotiation agents. We then facilitated over 180,000 negotiations between these agents across multiple scenarios with diverse…
Embodied AI Agents are quickly becoming important and common tools in society. These embodied agents should be able to learn about and accomplish a wide range of user goals and preferences efficiently and robustly. Large Language Models…
In the context of Visual Question Answering (VQA) and Agentic AI, calibration refers to how closely an AI system's confidence in its answers reflects their actual correctness. This aspect becomes especially important when such systems…
The relationship between humans and artificial intelligence is no longer science fiction -- it's a growing reality reshaping how we live and work. AI has moved beyond research labs into everyday life, powering customer service chats,…
As the use of interactive AI systems becomes increasingly prevalent in our daily lives, it is crucial to understand how individuals feel when interacting with such systems. In this work, we investigate the comfort level of individuals when…
AI agents are continually optimized for tasks related to human work, such as software engineering and professional writing, signaling a pressing trend with significant impacts on the human workforce. However, these agent developments have…
While research on human-AI collaboration exists, it mainly examined language learning and used traditional counting methods with little attention to evolution and dynamics of collaboration on cognitively demanding tasks. This study examines…